biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[ROCm][Quantization] Add asymmetric INT8 quantization support to TritonInt8ScaledMMLinearKernel (#38501)

Browse Source 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
Andreas Karatzas
2026-04-05 20:42:10 -05:00
committed by GitHub
parent 9570654c6d
commit 780ba37458
7 changed files with 133 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.buildkite/lm-eval-harness/configs/models-small-rocm.txt
View File

@@ -1,5 +1,6 @@
Qwen2.5-1.5B-Instruct.yaml
Meta-Llama-3.2-1B-Instruct-INT8-compressed-tensors.yaml
Meta-Llama-3-8B-Instruct-INT8-compressed-tensors-asym.yaml
Meta-Llama-3-8B-Instruct-nonuniform-compressed-tensors.yaml
Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
Qwen1.5-MoE-W4A16-compressed-tensors.yaml